{"schema":"https://assignee.net/schemas/benchmark-evidence-v1","schema_version":"1.0","contract_version":"benchmark-evidence-v1.0","contract_updated":"2026-06-01","schema_documentation":"https://assignee.net/schemas","changelog_url":"https://assignee.net/changelog","publisher":{"name":"Assignee Research","url":"https://assignee.net"},"html_url":"https://assignee.net/benchmarks/evidence?model=Gemini-1.5-Flash&bench=HumanEval","json_url":"https://assignee.net/benchmarks/evidence.json?model=Gemini-1.5-Flash&bench=HumanEval","model":"Gemini-1.5-Flash","benchmark":"HumanEval","source_count":2,"source_coverage":{"record_count":2,"distinct_source_count":2,"coverage_level":"LIMITED","basis":"distinct public paper URLs or titles in this evidence cluster"},"source_profile":{"source_url_count":2,"missing_source_url_count":0,"domains":["arxiv.org","doi.org"],"year_min":2024,"year_max":2024,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":17.4,"max_score_pct":73.0},"spread_pp":55.6,"severity":"HIGH","entries":[{"model":"Gemini-1.5-Flash","benchmark":"HumanEval","score_pct":73.0,"source_title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","source_url":"https://doi.org/10.48550/arxiv.2403.05530","source_domain":"doi.org","year":2024},{"model":"Gemini-1.5-Flash","benchmark":"HumanEval","score_pct":17.4,"source_title":"HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks","source_url":"http://arxiv.org/abs/2410.12381v3","source_domain":"arxiv.org","year":2024}],"interpretation":"This record groups score claims extracted from papers for the same model and benchmark label. A nonzero spread means the public literature reports different values for this cluster.","limitations":["Differences are not automatically errors.","Reported values may differ because of prompts, dataset versions, evaluation protocols, scoring rules, preprocessing, fine-tuning, or reporting conventions.","Source papers remain authoritative for their own claims."]}